agentmods.dev

cosmos-mcp: Instructions file for Claude Code

CLAUDE.md

cosmos-mcp CLAUDE.md is an instructions file for Claude Code from teampolarity/cosmos-mcp. It costs 1,310 tokens per session, scanned A, original, MIT.

Project instructions for cosmos-mcp, an MCP gateway that lets AI clients share a personal knowledge graph. MCP is a standard way for AI assistants to call tools and use connected data.

In plain words
What is it for?
They guide work on the TypeScript MCP server, command-line entry point, source connectors, authentication, daemon, and tool modules. They also explain how clients such as Claude Desktop, Cursor, Codex, Zed, and Continue connect to it.
Why use it?
They give contributors a map of the codebase and identify the authoritative tool list, data sources, authentication flow, and backend service. This reduces confusion when changing the server or its integrations.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

This is teampolarity/cosmos-mcp's own configuration. It tells Claude Code how to work on cosmos-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cosmos-mcp configures →

not rated 3repo 14d ago A scan 1,310 tokens original MIT
View source ↗ teampolarity/cosmos-mcp mcp.polarity-lab.com
Reuse

Borrowing it

Nothing to install: this file belongs to teampolarity/cosmos-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/teampolarity/cosmos-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/teampolarity/cosmos-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cosmos-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/teampolarity/cosmos-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/teampolarity/cosmos-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/teampolarity/cosmos-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/teampolarity/cosmos-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cosmos-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/teampolarity/cosmos-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/teampolarity/cosmos-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,310 This file is loaded in full into every session.
When invoked 1,310 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01310 $0.01310
Opus 5 $0.00655 $0.00655
Sonnet 5 $0.00262 $0.00262
Haiku 4.5 $0.00131 $0.00131

Measured 8d ago against content hash 95f0e075809f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cosmos-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cosmos-mcp

@polarity-lab/cosmos-mcp — the MCP gateway to Cosmos. Any MCP-capable client (Claude Desktop, Cursor, Codex, Zed, Continue, Claude Code) reads and writes the same personal knowledge graph hosted at cosmos.polarity-lab.com.

  • npm: @polarity-lab/cosmos-mcp under the wearepolarity account
  • Repo: teampolarity/cosmos-mcp (GitHub User, not Org — admin actions need a PAT minted from that account)
  • Landing: mcp.polarity-lab.com (README drives the page + Glama listing)
  • Backend talked to: cosmos.polarity-lab.com (the cosmos-fork Pages project)

Layout

  • bin/cosmos-mcp.js — CLI entrypoint. Dispatches subcommands and resolves the user key.
  • src/server.ts → dist/server.js — the MCP stdio server. npm start runs this.
  • src/tools/ — the 11 read/write tools exposed to MCP clients.
  • src/sources/ — local CLI source connectors (imessage, browser, calendar, claude-desktop, shell-history).
  • src/daemon/ — scaffolding for the signed Cosmos Sync.app LaunchAgent (0.6.0+, npm publish blocked on lab Apple Dev account transition).
  • src/auth/ — browser-based init bootstrap that mints a per-user key. The provision / install-handler / daemon subcommands live in bin/cosmos-mcp.js, not under src/auth/.
  • src/version.ts — single source of truth for the runtime version. Read from package.json at module load; used in the User-Agent header, --version output, and the MCP handshake. Don't hardcode versions anywhere else.
  • browser-extension/ — the Chrome and Firefox WebExtension surface (listed on CWS as cosmos by polarity lab, extension id jomeclciefpboanjnlfcdfgfjalldfno, and on Mozilla AMO). Lives in this repo, not as a separate cosmos-browser-extension repo. Shares filter-rules.json with src/sources/browser/ via browser-extension/scripts/sync-filter-rules.sh. Publish scripts are amo-publish.sh and chrome-publish.sh under browser-extension/scripts/.
  • tests/ — vitest. Run via npm test.

Tools (authoritative list in src/tools/index.ts)

Read the full file on GitHub · 64 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 64 lines · 1,310 tokens per session scan A 95f0e075809f

Subscribe to this mod's changes

cosmos-mcp CLAUDE.md is an instructions file published in the GitHub repository teampolarity/cosmos-mcp (3 stars, last pushed 14d ago), licensed MIT. It adds 1,310 tokens to every session, about $0.0066 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsMemory and contextai-memoryclaudeclaude-desktopcosmoscursorexocortex
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens